XLA
E431013
XLA (Accelerated Linear Algebra) is a domain-specific compiler for linear algebra that optimizes and accelerates machine learning computations on hardware such as TPUs and GPUs.
All labels observed (2)
| Label | Occurrences |
|---|---|
| PyTorch/XLA project ecosystem | 1 |
| XLA canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T4326079 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: XLA Context triple: [TPUs (via XLA integrations), usesFramework, XLA]
-
A.
TPUs (via XLA integrations)
TPUs (via XLA integrations) are Google's specialized tensor processing units that can be used as accelerators for PyTorch models through the XLA compilation framework.
-
B.
PlaidML
PlaidML is an open-source, hardware-agnostic deep learning engine designed to accelerate neural network computation on a wide range of GPUs and other devices.
-
C.
Chainer
Chainer is an open-source deep learning framework for Python that pioneered a flexible "define-by-run" computation graph approach to building neural networks.
-
D.
MXNet
MXNet is an open-source deep learning framework designed for efficient, scalable training and inference across multiple GPUs and distributed systems.
-
E.
Swift for TensorFlow
Swift for TensorFlow is an experimental machine learning platform that integrates TensorFlow directly into the Swift programming language to enable differentiable programming and high-performance model development.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: XLA Target entity description: XLA (Accelerated Linear Algebra) is a domain-specific compiler for linear algebra that optimizes and accelerates machine learning computations on hardware such as TPUs and GPUs.
-
A.
TPUs (via XLA integrations)
TPUs (via XLA integrations) are Google's specialized tensor processing units that can be used as accelerators for PyTorch models through the XLA compilation framework.
-
B.
PlaidML
PlaidML is an open-source, hardware-agnostic deep learning engine designed to accelerate neural network computation on a wide range of GPUs and other devices.
-
C.
Chainer
Chainer is an open-source deep learning framework for Python that pioneered a flexible "define-by-run" computation graph approach to building neural networks.
-
D.
MXNet
MXNet is an open-source deep learning framework designed for efficient, scalable training and inference across multiple GPUs and distributed systems.
-
E.
Swift for TensorFlow
Swift for TensorFlow is an experimental machine learning platform that integrates TensorFlow directly into the Swift programming language to enable differentiable programming and high-performance model development.
- F. None of above. chosen
Statements (48)
| Predicate | Object |
|---|---|
| instanceOf |
domain-specific compiler
ⓘ
linear algebra compiler ⓘ machine learning compiler ⓘ |
| abbreviationOf | Accelerated Linear Algebra NERFINISHED ⓘ |
| developedBy | Google NERFINISHED ⓘ |
| fullName | Accelerated Linear Algebra NERFINISHED ⓘ |
| goal |
enable hardware-specific optimizations
ⓘ
improve performance of numerical computations ⓘ provide portable performance across accelerators ⓘ reduce memory usage ⓘ |
| hasBackend |
XLA:CPU backend
ⓘ
XLA:GPU backend ⓘ XLA:TPU backend ⓘ |
| hasComponent |
HLO interpreter
ⓘ
HLO optimizer ⓘ backend code generator ⓘ |
| hostedAt | GitHub NERFINISHED ⓘ |
| inputType | tensor computation graphs ⓘ |
| integratedWith |
JAX
NERFINISHED
ⓘ
PyTorch (via experimental backends and projects) NERFINISHED ⓘ TensorFlow NERFINISHED ⓘ |
| license | Apache License 2.0 ⓘ |
| originatedInProject | TensorFlow XLA project ⓘ |
| outputType |
hardware-specific kernels
ⓘ
optimized machine code ⓘ |
| partOf | TensorFlow ecosystem NERFINISHED ⓘ |
| performsOptimization |
algebraic simplification
ⓘ
buffer reuse ⓘ common subexpression elimination ⓘ constant folding ⓘ layout optimization ⓘ loop fusion ⓘ operation fusion ⓘ |
| relatedTo | OpenXLA project NERFINISHED ⓘ |
| repository | https://github.com/openxla/xla ⓘ |
| supportsLanguage | HLO (High Level Optimizer) IR NERFINISHED ⓘ |
| targetsHardware |
CPU
ⓘ
GPU NERFINISHED ⓘ TPU NERFINISHED ⓘ |
| usedFor |
accelerating machine learning workloads
ⓘ
ahead-of-time compilation ⓘ compiling tensor computations ⓘ graph-level optimization ⓘ just-in-time compilation ⓘ kernel fusion ⓘ memory optimization ⓘ operator fusion ⓘ optimizing linear algebra computations ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: XLA Description of subject: XLA (Accelerated Linear Algebra) is a domain-specific compiler for linear algebra that optimizes and accelerates machine learning computations on hardware such as TPUs and GPUs.
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
PyTorch/XLA project ecosystem